Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description corroborates with 'Lecture seule' rather than contradicting. It adds genuine context beyond annotations: the check is indicative only and a signed power balance takes precedence, which matters for how an agent should weigh the result.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the call trigger, then criteria, then the scene shape, then the caveat — a sensible order with no filler sentences. The one waste is repeating the same field list already given in the input schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single read-only, closed-world check with no output schema, the description supplies the decision criteria, the expected input shape, and the authority caveat. What remains unsaid is the response format (pass/fail per criterion), which the agent must discover at call time.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the description's 'groupes_electrogene [{nom, puissance_kva, ...}]' restates exactly what the schema property already documents. Because the tool is optional-parameter (0 required) and the scene structure appears twice verbatim, no additional semantic value is added beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource in caps ('VERIFIER LE GROUPE ELECTROGENE DE SECOURS') and enumerates the four checks with named rule codes (GE-PUISSANCE, GE-COMMUTATION, GE-AUTONOMIE, GE-CARBURANT). An agent can tell this apart from adjacent BIM checks like cao_bim_energie or cao_bim_mep without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Appelez quand vous devez VERIFIER...' gives an explicit trigger condition rather than implied usage. It also warns that the verdict is 'Indicatif — bilan de puissance signe prime', which signals when its output must be superseded, though it names no alternative sibling tool to call in that case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.